apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-04-27 22:06:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix error with pandas dataframes (#92)

Browse source 
* Fix error with pandas dataframes in _columns_different_distributions + add appropriate test
* Update documentation of classes to reflect that all data should be encoded and scaled.

---------

Signed-off-by: abigailt <abigailt@il.ibm.com>
This commit is contained in:
abigailgold 2024-02-13 08:56:12 -05:00 • committed by GitHub
parent cb70ca10e6
commit e00535d120
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 28 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

28
apt/risk/data_assessment/attack_strategy_utils.py
View file

@ -5,7 +5,6 @@ import numpy as np
from scipy import stats
from sklearn.neighbors import NearestNeighbors
from tqdm import tqdm
from pandas.api.types import is_numeric_dtype, is_categorical_dtype
from apt.utils.datasets import ArrayDataset
@ -169,26 +168,15 @@ class KNNAttackStrategyUtils(AttackStrategyUtils):
differing_columns = []
df1_samples = df1.get_samples()
df2_samples = df2.get_samples()
if df1.is_pandas:
for name, _ in df1_samples.items():
is_categorical = name in categorical_features or is_categorical_dtype(df1_samples.dtypes[name])
is_numeric = is_numeric_dtype(df1_samples.dtypes[name])
KNNAttackStrategyUtils._column_statistical_test(df1_samples[name], df2_samples[name], name,
is_categorical, is_numeric,
self.distribution_comparison_numeric_test,
self.distribution_comparison_categorical_test,
self.distribution_comparison_alpha,
differing_columns)
else:
is_numeric = np.issubdtype(df1_samples.dtype, int) or np.issubdtype(df1_samples.dtype, float)
is_numeric = np.issubdtype(df1_samples.dtype, int) or np.issubdtype(df1_samples.dtype, float)
for i, column in enumerate(df1_samples.T):
is_categorical = i in categorical_features
KNNAttackStrategyUtils._column_statistical_test(df1_samples[:, i], df2_samples[:, i], i,
is_categorical, is_numeric,
self.distribution_comparison_numeric_test,
self.distribution_comparison_categorical_test,
self.distribution_comparison_alpha, differing_columns)
for i, column in enumerate(df1_samples.T):
is_categorical = i in categorical_features
KNNAttackStrategyUtils._column_statistical_test(df1_samples[:, i], df2_samples[:, i], i,
is_categorical, is_numeric,
self.distribution_comparison_numeric_test,
self.distribution_comparison_categorical_test,
self.distribution_comparison_alpha, differing_columns)
return differing_columns
def validate_distributions(self, original_data_members: ArrayDataset, original_data_non_members: ArrayDataset,